© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 24509
    Prev
    Next
    INDEX
    Explanations

    phrases comparing something or someone to a similar entity or concept

    oai_token-act-pair · gpt-3.5-turbo

    the word "like" used in various contexts to indicate comparison or similarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exting
    -0.87
     Seym
    -0.83
     destro
    -0.81
    tein
    -0.80
     corrid
    -0.79
    Ire
    -0.76
     enthusi
    -0.75
     proport
    -0.74
     millenn
    -0.72
    elsius
    -0.71
    POSITIVE LOGITS
    lihood
    1.79
    liest
    0.93
     minded
    0.88
    minded
    0.82
    liness
    0.81
    ability
    0.78
    lier
    0.78
    pires
    0.74
     wildfire
    0.67
    able
    0.64
    Activations Density 0.032%

    No Known Activations